CoANE: Modeling Context Co-occurrence for Attributed Network Embedding

@article{Hsieh2021CoANEMC,
  title={CoANE: Modeling Context Co-occurrence for Attributed Network Embedding},
  author={I-Chung Hsieh and Cheng-Te Li},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.09241}
}
Attributed network embedding (ANE) is to learn low-dimensional vectors so that not only the network structure but also node attributes can be preserved in the embedding space. Existing ANE models do not consider the specific combination between graph structure and attributes. While each node has its structural characteristics, such as highly-interconnected neighbors along with their certain patterns of attribute distribution, each node’s neighborhood should be not only depicted by multi-hop… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 38 REFERENCES
Label Informed Attributed Network Embedding
TLDR
A novel Label informed Attributed Network Embedding (LANE) framework that can smoothly incorporate label information into the attributed network embedding while preserving their correlations is proposed and achieves significantly better performance compared with the state-of-the-art embedding algorithms. Expand
A United Approach to Learning Sparse Attributed Network Embedding
TLDR
A novel Sparse Attributed Network Embedding (SANE) framework to learn the network structure and sparse attribute information simultaneously in a united approach is proposed and an attention mechanism is introduced to adaptively weigh the strength of interactions between each context node and the center node, according to the node attribute similarity. Expand
Attributed Social Network Embedding
TLDR
This paper proposes a generic Attributed Social Network Embedding framework (ASNE), which learns representations for social actors by preserving both the structural proximity and attribute proximity, and shows significant gains on the tasks of link prediction and node classification. Expand
gat2vec: representation learning for attributed graphs
TLDR
The gat2vec framework is introduced that uses structural information to generate structural contexts, attributes to generate attribute contexts, and employs a shallow neural network model to learn a joint representation from them and is effective in exploiting multiple sources of information. Expand
Deep Attributed Network Embedding
TLDR
This paper proposes a novel deep attributed network embedding approach, which can capture the high nonlinearity and preserve various proximities in both topological structure and node attributes, and a novel strategy is proposed to guarantee the learned node representation can encode the consistent and complementary information from the topological structures and nodes attributes. Expand
ANRL: Attributed Network Representation Learning via Deep Neural Networks
TLDR
This paper proposes a novel framework, named ANRL, to incorporate both the network structure and node attribute information in a principled way, and proposes a neighbor enhancement autoencoder to model the nodes attribute information, which reconstructs its target neighbors instead of itself. Expand
Exploring Expert Cognition for Attributed Network Embedding
TLDR
A novel problem of exploring expert cognition for attributed network embedding is studied and a principled framework NEEC is proposed, formulated as a task of asking experts a number of concise and general queries that can be generalized to various real-world networks. Expand
Content to Node: Self-Translation Network Embedding
TLDR
A novel sequence-to-sequence model based NE framework which is referred to as Self-Translation Network Embedding (STNE) model, which outperforms the state-of-the-art NE approaches and fuses the content and structure information seamlessly from the raw input. Expand
Learning Edge Representations via Low-Rank Asymmetric Projections
TLDR
This work proposes a new method for embedding graphs while preserving directed edge information, and explicitly model an edge as a function of node embeddings, and proposes a novel objective, the graph likelihood, which contrasts information from sampled random walks with non-existent edges. Expand
Semi-supervisedly Co-embedding Attributed Networks
TLDR
A semi-supervised co-embedding model for attributed networks (SCAN) based on the generalized SVAE for the heterogeneous data, which collaboratively learns low- dimensional vector representations of both nodes and attributes for partially labelled attributed networks semi- supervisedly is presented. Expand
...
1
2
3
4
...